Tavily Connector for AI agents.
6 live capabilities
Conduct real-time web research and content extraction for your agent.
Waiting for input…
Why people use Tavily
Tavily for Real-Time Web Research
This Connector flips that. Your agent does the browsing for you. It grabs the data, cleans it up, and hands you the answer. You stop being a data middleman and start being the person who makes the decisions.
What Vinkius changes
Your agent gets a high-quality research department built into its workflow.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Researching a niche market
An analyst asks for a summary of a competitor's new product.
- Real-world use case 02
Real-time news monitoring
A news bot needs to know about a breaking tech story.
- Real-world use case 03
Content planning
A strategist needs visual ideas for a blog.
Complete set · 6capabilities
The complete Tavily capability set.
These are the exact actions your AI can choose when you ask it to work with Tavily.
01—03
3 capabilities in this set.
Part of 6 available through Tavily.
- 01 Capability
Extract content
Pulls clean, readable text from a specific URL. It's perfect for getting the meat of a page without the headers or ads.
- 02 Capability
Get answer
Gets a direct AI-generated answer to a query. Use this when you want the bottom line instead of a list of links.
- 03 Capability
Get search context
Retrieves search results optimized for LLMs. This gives your agent the right context to stay grounded in facts.
04—06
3 capabilities in this set.
Part of 6 available through Tavily.
- 04 Capability
Search images
Finds high-quality images for your agent. It helps maintain visual context during complex research tasks.
- 05 Capability
Search news
Pulls real-time news results. It's the best way to keep your agent updated on current events.
- 06 Capability
Search web
Performs a general web search optimized for AI. It filters out the noise to find what your agent actually needs.
Set up in minutes
One URL. Then ask Tavily to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Tavily from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_RuwCPMnEJIsW1Ybn1uqAXIOKlSvsLiedRq57Wyit/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Tavily, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Tavily for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_RuwCPMnEJIsW1Ybn1uqAXIOKlSvsLiedRq57Wyit/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Tavily URL.
- Step 03
Save and start
Save the connection and enable Tavily in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"tavily": {
"url": "https://edge.vinkius.com/vk_preview_RuwCPMnEJIsW1Ybn1uqAXIOKlSvsLiedRq57Wyit/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Tavily
Open Agent mode in chat and ask: "Using Tavily, help me...". 6 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"tavily": {
"url": "https://edge.vinkius.com/vk_preview_RuwCPMnEJIsW1Ybn1uqAXIOKlSvsLiedRq57Wyit/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Tavily
Ask Copilot: "Using Tavily, help me...". 6 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"tavily": {
"url": "https://edge.vinkius.com/vk_preview_RuwCPMnEJIsW1Ybn1uqAXIOKlSvsLiedRq57Wyit/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Tavily
Open Cascade and ask: "Using Tavily, help me...". 6 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"tavily": {
"url": "https://edge.vinkius.com/vk_preview_RuwCPMnEJIsW1Ybn1uqAXIOKlSvsLiedRq57Wyit/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Tavily
Ask Cline: "Using Tavily, help me...". 6 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add tavily --transport http "https://edge.vinkius.com/vk_preview_RuwCPMnEJIsW1Ybn1uqAXIOKlSvsLiedRq57Wyit/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Tavily
Ask Claude: "Using Tavily, show me...". 6 tools are ready
Where the request belongs
Work Tavily can move forward.
It's for the researchers who are tired of manual copy-pasting, the developers building agentic workflows, and the content leads who need to stay on top of trends without spending all day on Google.
AI Developer
Building agents that need to browse the live web to provide accurate, real-time answers for users.
Market Researcher
Pulling data from dozens of sources to create reports without opening a single browser tab.
Content Strategist
Auditing trending topics and finding visual assets for rapid content planning.
When one Connector is not enough
Carry the request into a workflow.
Combine Tavily with the systems that finish the task.
View all recipesConnectors for AI-Powered Trend Detection
By the time a trend reaches your Twitter feed it is too late to act , Tavily detects signals from primary sources, Chroma builds a semantic map that reveals connections between weak signals, and Notion tracks emerging trends weeks before they go mainstream
Scrape and Structure Web Data Using Connectors
Scraping capabilities break when websites change layouts. Browserbase gives your AI agent a real browser , it navigates, clicks, fills forms, reads dynamic content and extracts data from pages that defeat every traditional scraper
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsJina AI
Search and read the web for AI. audit search results and reader content via AI.
Exa AI
Search the web with neural embeddings that understand meaning, not just keywords, and return the most relevant results for any query.
Bing Search
Empower your AI agent with real-time web, image, and news search via Bing.
Exa
Find exactly the web content you need with semantic search that understands context and returns high-quality curated results.
SerpApi
Equip your AI agent with real-time web search capabilities across Google, Bing, Baidu, Yahoo, and DuckDuckGo.
ValueSERP
Bring real-time Google Search data into your AI agent. Search organically, find images, news, scholars, and related questions without getting blocked.
Bring your own AI
Change the model, client or framework. Keep Tavily connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Tavily.
The practical details behind the request, access and result.
How does Tavily MCP help my AI agent browse the web?
It gives your agent a way to see the live web without the clutter. It filters out ads and junk, providing only the high-quality data your agent needs to perform tasks.
Can Tavily MCP extract text from specific websites?
Yes, it pulls clean text from URLs so your agent doesn't have to read raw HTML. This makes it much easier for your agent to summarize articles or find specific facts.
Is Tavily MCP good for real-time news?
It's built for it. It can pull the latest headlines and updates instantly, ensuring your agent has access to current events rather than just outdated training data.
What makes Tavily MCP different from a regular search?
It's optimized for LLMs. Unlike a standard search that shows results for humans, Tavily provides filtered, structured context that your agent can actually use to answer questions.
Can my agent find images using Tavily MCP?
Yes, it can search for high-quality images to help provide visual context for a topic. This is great for research tasks where visual data is important.
How do I get the best search results from Tavily MCP?
Use the search_web capability to get results that are already curated for your agent's needs. It handles the heavy lifting of filtering out the noise for you.
How do I find my Tavily API Key?
Log in to your Tavily dashboard, and you will find your API Key on the overview page. Copy and paste it below.
What is Search Context vs Web Search?
Search Context is optimized for direct ingestion by LLMs, providing a denser format of information, while Web Search provides standard curated results with snippets and scores.
Can the agent extract content from any website?
Yes. The extract_content capability allows your agent to retrieve the cleaned main text from any accessible URL, bypassing ads and navigation elements for structured analysis.
One connection away
Give your agent a direct line to Tavily.
Connect Tavily once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available